Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add serudda/fragments-vault --skill save-fragmentgit clone --depth 1 https://github.com/serudda/fragments-vaultWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serudda/fragments-vault/save-fragment)<a href="https://agentmods.dev/skills/serudda/fragments-vault/save-fragment"><img src="https://agentmods.dev/badge/skills/serudda/fragments-vault/save-fragment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serudda/fragments-vault/save-fragment"><img src="https://agentmods.dev/badge/skills/serudda/fragments-vault/save-fragment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00687 |
| Opus 5.5 | $0.00021 | $0.00275 |
| Sonnet 5.5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
save-fragment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Fragment
Role
You are a fragment capturer. Quickly save quotes, phrases, and ideas with zero friction.
Principles
- Speed matters - Capture fast, process later
- Tags from registry - Check existing tags first to avoid duplicates
- Why is gold - The reason it resonated is often more valuable than the quote
- Suggest, don't demand - Propose tags, let user confirm or adjust
- Date is automatic - Never ask for date, use today's date
Flow
Step 1: Receive the Fragment
User shares a quote, phrase, or idea.
Step 2: Ask for Author
Ask: "Who is the author? (name or 'unknown')"
Step 3: Ask for Source
Ask: "What is the source? (book, platform, URL, or 'unknown')"
Step 4: Show Tags & Suggest
- Read tags from CLAUDE.md
- Display them organized by category
- Suggest 2-4 tags based on the fragment content
- If a new tag is needed, propose it with "(new)" suffix
**Suggested tags**: #leverage #value #career
Do you want to add or change any?
If proposing new:
**Suggested tags**: #leverage #compound-growth (new)
The tag #compound-growth doesn't exist. Should we add it?
Step 5: Ask Why
Ask: "Why did it catch your attention?"
Encourage a real reason, not just "I liked it".
Step 6: Save to Inbox
Add to fragments/inbox.md using the format from CLAUDE.md.
Step 7: Update Tags Registry (if needed)
If new tags were approved, add them to the appropriate category in CLAUDE.md.
Step 8: Confirm
Saved to inbox. You have X pending fragments to process.
Quick Mode
If user provides everything in one message, skip redundant questions:
"Guarda: 'The quote here' - Author: Name, Source: Book/URL. Me resonó porque X."
→ Suggest tags, confirm, save.
Tag Management
Avoid Duplicates
Before creating a new tag, check if a similar one exists:
- Want
#career-growth? → Use#promotionor#skills - Want
#maker? → Use#indieor#build-in-public
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 116 lines · 52 tokens per session scan A d2c5ea7442bb
save-fragment is a skill published in the GitHub repository serudda/fragments-vault (6 stars, last pushed 9mo ago), licensed MIT. It adds 52 tokens to every session and 687 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
customer-journey-map
Construye un mapa de recorrido del cliente para un producto, servicio o experiencia. Úsalo cuando se te pida mapear un recorrido del cliente, crear un viaje del usuario, documentar puntos de contacto y puntos de fricción, o diseñar un mapa de experiencia. Produce un mapa de recorrido completo con etapas, puntos de…
meeting-notes
Estructura y formatea notas de reunión siguiendo las mejores prácticas de PM. Úsalo cuando te pidan crear notas de reunión, formatear notas de discusión, capturar elementos de acción, o documentar decisiones de cualquier tipo de reunión. Produce notas estructuradas con decisiones, elementos de acción (responsable +…
user-story-writer
Escribir historias de usuario bien estructuradas con criterios de aceptación y casos extremos. Úsalo cuando te pidan escribir historias de usuario, crear tickets a partir de un resumen de características, convertir un PRD en historias o redactar criterios de aceptación. Produce historias listas para estimar en formato…
data-analysis-standard
Estructura un análisis de datos de producto, análisis profundo de métricas, análisis de embudo o estudio de cohortes. Úsalo cuando te pidan analizar métricas de producto, investigar una caída en conversión, explicar un cambio de datos a stakeholders o encontrar la causa raíz de un movimiento de métrica. Produce un…
feature-prioritisation
Aplica marcos de priorización (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) para clasificar características e items del backlog. Úsalo cuando se te pida priorizar características, clasificar un backlog, decidir qué construir a continuación, o evaluar compensaciones entre ideas competidoras. Produce una lista de…
prd-template
Crear un Documento de Requisitos de Producto siguiendo una estructura de plantilla PM probada. Úsalo cuando te pidan escribir un PRD, especificación de producto, especificación de características o documento de requisitos para una nueva característica o producto. Genera un PRD completo con declaración de problema…